How to Use the Marketplacer (Enterprise Marketplace Platform) MCP in Google ADK

Q: How do I configure Marketplacer (Enterprise Marketplace Platform) within the Google ADK?

Install the package, initialize the McpToolset with your HTTP MCP Server URL, and pass it to your LlmAgent. The tools are immediately available for Gemini to invoke during execution.

Q: Can I restrict the agent to only read product data?

Yes. You can filter the exposed tools in your McpToolset configuration. For example, you can expose only listadverts and getadvert, completely hiding financial tools like listinvoices.

Run Gemini-powered marketplace operations on Google Cloud with the Google ADK and Marketplacer.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marketplacer (Enterprise Marketplace Platform) MCP to Google ADK

Create your Vinkius account to connect Marketplacer (Enterprise Marketplace Platform) to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Marketplacer (Enterprise Marketplace Platform) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze seller networks with Google ADK

This Marketplacer MCP Server connects your Gemini models directly to your vendor database. By calling `list_sellers`, your agent pulls real-time vendor profiles and feeds them into BigQuery for instant compliance checks. The Google ADK handles the plumbing, allowing you to combine live marketplace data with your enterprise data warehouse. You get a clear picture of seller performance without manual exports or custom scripts.

Audit order pipelines at scale

The `list_invoices` and `list_shipments` tools let your agent track orders from payment to delivery. Gemini uses its long-context window to analyze thousands of transaction records in a single run, spotting shipping delays instantly. This setup avoids API rate limits by letting the agent process massive batches. You get direct answers about fulfillment bottlenecks without writing complex database queries.

Query catalogs using long-context reasoning

This MCP Server uses `graphql_query` and `list_adverts` to feed your entire product catalog into Gemini's 1M+ token context. Your agent cross-references taxonomies from `list_categories` to suggest better catalog structures. The ADK exposes these tools natively to your `LlmAgent`. The agent executes complex queries, processes the raw JSON payload, and updates product attributes based on your business rules.

Setup guide

Set up Marketplacer (Enterprise Marketplace Platform) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Marketplacer (Enterprise Marketplace Platform) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Marketplacer (Enterprise Marketplace Platform)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Marketplacer (Enterprise Marketplace Platform) tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Marketplacer. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Marketplacer (Enterprise Marketplace Platform) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Marketplacer (Enterprise Marketplace Platform) MCP in Google ADK

Install the package, initialize the `McpToolset` with your HTTP MCP Server URL, and pass it to your `LlmAgent`. The tools are immediately available for Gemini to invoke during execution.

Yes. You can pass multiple toolsets to your agent, allowing it to pull vendor lists via `list_sellers` and write that data directly into a BigQuery table in the same turn.

The MCP Server manages the API tokens inside an isolated Vinkius sandbox. Your ADK code only needs the single endpoint token, keeping your main enterprise credentials hidden from the agent environment.

Yes. You can filter the exposed tools in your `McpToolset` configuration. For example, you can expose only `list_adverts` and `get_advert`, completely hiding financial tools like `list_invoices`.

All transit data, including shipment tracking numbers and billing records, is processed in memory within your private Google Cloud perimeter. No persistent storage is used on the Vinkius platform, ensuring zero data retention.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript